How to use CIDAS/clipseg-rd64-refined with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="CIDAS/clipseg-rd64-refined")
# Load model directly from transformers import AutoProcessor, CLIPSegForImageSegmentation processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined") model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")
We give an input image, mask text, and then it will extract that masked area from the image and save into a folder
I have used invoke ai but the results are not like i am expecting
input
command
!mask "C:\Users\King\Downloads\a.jpg" -tm "clothes" 0.99
outputs
my expected output
· Sign up or log in to comment